论文信息 - DirecTL: a Language Independent Approach to Transliteration

DirecTL: a Language Independent Approach to Transliteration

We present DirecTL: an online discriminative sequence prediction model that employs a many-to-many alignment between target and source. Our system incorporates input segmentation, target character prediction, and sequence modeling in a unified dynamic programming framework. Experimental results suggest that DirecTL is able to independently discover many of the language-specific regularities in the training data.

Grzegorz Kondrak | Qing Dou | Sittichai Jiampojamarn | Aditya Bhargava | Kenneth Dwyer

[1] Jian Su,et al. A Joint Source-Channel Model for Machine Transliteration , 2004, ACL.

[2] Grzegorz Kondrak,et al. Joint Processing and Discriminative Training for Letter-to-Phoneme Conversion , 2008, ACL.

[3] A. Kumaran,et al. A generic framework for machine transliteration , 2007, SIGIR.

[4] Koby Crammer,et al. Ultraconservative Online Algorithms for Multiclass Problems , 2001, J. Mach. Learn. Res..

[5] Thorsten Joachims,et al. Making large-scale support vector machine learning practical , 1999 .

[7] Grzegorz Kondrak,et al. Applying Many-to-Many Alignments and Hidden Markov Models to Letter-to-Phoneme Conversion , 2007, NAACL.

[8] Grzegorz Kondrak,et al. A New Algorithm for the Alignment of Phonetic Sequences , 2000, ANLP.

[9] Haizhou Li,et al. Whitepaper of NEWS 2009 Machine Transliteration Shared Task , 2009, NEWS@IJCNLP.

[10] Thorsten Joachims,et al. Making large scale SVM learning practical , 1998 .

[11] Hermann Ney,et al. Improvements in Phrase-Based Statistical Machine Translation , 2004, NAACL.